Impulse and Pico collaborate to provide Xilinx Virtex-4 based acceleration

C-to-hardware solution accelerates algorithms up to 400x

Impulse and Pico Computing have released support for compilation of high-performance C algorithms to Pico's new E-12 line of CompactFlash FPGA accelerator cards, using Impulse C tools. The resulting software-programmable hardware accelerator offers the potential for 10X to 400X increases in processing speed of desktop and embedded applications, in a form factor the size of a standard CompactFlash memory card. The combined solution is available from Direct Insight.

The Pico E-12 PCMCIA cards provide massively parallel hardware computing resources in a low-power (less than one watt), self-contained CompactFlash package. Impulse C and the Impulse CoDeveloper tools give software programmers access to this computing resource by allowing hardware accelerators to be compiled directly from C. Impulse tools optimize the C code to exploit the FPGA's parallel processing capability, resulting in potentially large factors of acceleration. The Impulse tools also generate the required software-to-hardware interfaces, allowing data to be moved efficiently between the FPGA and the optional on-board PowerPC processor, and between the E-12 card and a host PC. Applications where this type of approach is showing promise include image processing, video processing, data encryption, bioinformatics, geophysics and other types of embedded and scientific computing.

The Pico E-12 is based on the latest-generation Xilinx Virtex-4 FPGA. There are two versions of the Pico E-12: Logic Optimized (LO) and Embedded Processor (EP). The Logic Optimized versions offer the most user-configurable logic, while the Embedded Processor version provides a reduced amount of FPGA logic but adds an embedded PowerPC processor. In either case, the FPGA device is completely reconfigurable through the E-12's CompactFlash interface, with no external power or cabling required, either for programming or for normal operation.

The ability to program hardware using traditional C-based methods is critical to the widespread acceptance of FPGAs as computing platforms. By using the Impulse C tools, software programmers now have the ability to compile computationally-intensive C subroutines and processes directly into the FPGA, without the need to be FPGA hardware designers.

For further information, see our Impulse C pages.